© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 25292
    Prev
    Next
    INDEX
    Explanations

    explanation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Const
    -0.08
     discerning
    -0.08
     fucking
    -0.08
     აი
    -0.08
     CONST
    -0.07
    enaamde
    -0.07
     trx
    -0.07
     woke
    -0.07
    dds
    -0.07
     gaw
    -0.07
    POSITIVE LOGITS
     briefly
    0.10
     Kiel
    0.08
     lightly
    0.07
    _WE
    0.07
     Chopra
    0.07
     shortly
    0.07
    .enc
    0.07
     Uncomment
    0.07
     quickly
    0.07
    Brief
    0.07
    Activations Density 0.024%

    No Known Activations